ConsensusAndProfile.hs

import qualified Bioinformatics.DNANucleotide as D
import qualified Bioinformatics.FASTA as F
import qualified Data.List as L

getLines contents = do
  line <- getLine
  if null line
    then return contents
    else getLines $ contents ++ line ++ "\n"

convertToProfile :: [[D.DNANucleotide]] -> String
convertToProfile dnaStrings =
  unlines $ map buildString [D.A, D.C, D.G, D.T]
  where columns = L.transpose dnaStrings
        lengths nucleotide = map (length . filter (== nucleotide))
        buildString n = show n ++ ": " ++ (unwords . map show $ lengths n columns)

determineConcensus :: [[D.DNANucleotide]] -> String
determineConcensus =
  concat . map show . mostCommon . L.transpose
  where mostCommon = map (head . L.maximumBy (\a1 a2 -> length a1 `compare` length a2) . L.group . L.sort)

main = do
  lines <- getLines ""
  let fastas = F.buildFASTALines lines
  let dnaStrings = tail $ map F.content fastas
  putStrLn $ determineConcensus dnaStrings
  putStrLn $ convertToProfile dnaStrings